This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
nlpet
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
21
Latent Adversarial Training (LAT) Improves the Representation of Refusal
8mo
6
42
Characterizing stable regions in the residual stream of LLMs
1y
4
29
Evaluating Synthetic Activations composed of SAE Latents in GPT-2
1y
0
Comments